I throw all my queries at Grok 4 Expert, GPT 5 Thinking and Opus 4.1 Extended Thinking.. for Golang it's been my experience that Grok produce the best results about 90% of the time as well.
Not sure about Claude, but OpenAI models are pretty bad at Go for some reason. For example, they always want to replace the "new" style for-loop that uses range with the old syntax. This drives me nuts.
Some simple example:
https://claude.ai/share/6d178173-cdf7-4e50-a467-73ee9f479d56.
https://chatgpt.com/share/69102735-46ac-8012-9cf0-0969585c86....
https://grok.com/share/bGVnYWN5LWNvcHk%3D_54b5f2f1-732e-4372....
I don't use Gemini but haven't been impressed whenever I tried it with GitHub Copilot.